INDEX

Explanations

references to investigations or inquiries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GOTREF

-0.81

flashdata

-0.72

 وسلم

-0.71

uxxxx

-0.68

Bü

-0.66

ness

-0.64

########.

-0.63

posedge

-0.61

 birth

-0.61

 chóng

-0.60

POSITIVE LOGITS

 investigations

2.24

 investigation

2.20

 Investigation

1.97

 INVESTIGATION

1.96

investig

1.95

 Investigate

1.93

investigation

1.92

 investigate

1.92

 Investigations

1.91

Investigations

1.90

Activations Density 0.070%

references to investigations or inquiries

No Comments

No Known Activations